Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel predictio...Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel prediction model for ultrashort-term wind-speed prediction in wind farms is developed by combining a deep belief network,the Elman neural network,and the Hilbert-Huang transform modified using an improved particle swarm optimization algorithm.The experimental results show that the prediction results of the proposed deep neural network is better than that of shallow neural networks.Although the complexity of the model is high,the accuracy of wind-speed prediction and stability are also high.The proposed model effectively improves the accuracy of ultrashort-term wind-speed forecasting in wind farms.展开更多
Based on wind-speed records of Alaska’s 19 first-order weather stations, we analyzed the near-surface wind-speed stilling for January 1, 1984 to December 31, 2016. With exception of Big Delta that indicates an increa...Based on wind-speed records of Alaska’s 19 first-order weather stations, we analyzed the near-surface wind-speed stilling for January 1, 1984 to December 31, 2016. With exception of Big Delta that indicates an increase of 0.0157 m·s–1·a–1, on average, all other first-order weather stations show declining trends in the near-surface wind speeds. In most cases, the average trends are less then?–0.0300?m·s–1·a–1. The strongest average trend of?–0.0500?m·s–1·a–1 occurred at Homer, followed by?–0.0492?m·s–1·a–1 at Bettles, and?–0.0453?m·s–1·a–1 at Yakutat, while the declining trend at Barrow is marginal. The impact of the near-surface wind-speed stilling on the wind-power potential expressed by the wind-power density was predicted and compared with the wind-power classification of the National Renewable Energy Laboratory and the Alaska Energy Authority. This wind-power potential is, however, of subordinate importance because wind turbines only extract a fraction of the kinetic energy from the wind field characterized by the power efficiency. Since wind turbine technology has notably improved during the past 35 years, we hypothetically used seven currently available wind turbines of different rated power and three different shear exponents to assess the wind-power sustainability under changing wind regimes. The shear exponents 1/10, 1/7, and 1/5 served to examine the range of wind power for various conditions of thermal stratification. Based on our analysis for January 1, 1984 to December 31, 2016, Cold Bay, St. Paul Island, Kotzebue, and Bethel would be very good candidates for wind farms. To quantify the impact of a changing wind regime on wind-power sustainability, we predicted wind power for the periods January 1, 1984 to December 31, 1994 and January 1, 2006 to December 31, 2016 as well. Besides Big Delta that suggests an increase in wind power of up to 12% for 1/7, predicted wind power decreased at all sites with the highest decline at Annette (≈38%), Kodiak (≈30%), King Salmon (≈26%), and Kotzebue (≈24%), where the effect of the shear exponents was marginal. Bethel (up to 20%) and Cold Bay (up to 14%) also show remarkable decreases in predicted wind power.展开更多
基金This study was supported by the Research and Application of Key Technologies in the Design of Large Onshore Smart Wind Power Base(Grant No.XBY-ZDKJ-2020-05)the Scientific Research Project of the China Electric Power Construction Corporation:Research and Application of Key Technologies in the Design of an Onshore Smart Wind Power Base(Grant No.DJ-ZDXM-2020-52)+2 种基金the Danish Energy Agency(Grant No.64013-0405)the Fundamental Research Funds for the Central Universities(Grant No.B210201018)the Jiangsu Province Policy Guidance Program(Grant No.BZ2021019).
文摘Random and fluctuating wind speeds make it difficult to stabilize the wind-power output,which complicates the execution of wind-farm control systems and increases the response frequency.In this study,a novel prediction model for ultrashort-term wind-speed prediction in wind farms is developed by combining a deep belief network,the Elman neural network,and the Hilbert-Huang transform modified using an improved particle swarm optimization algorithm.The experimental results show that the prediction results of the proposed deep neural network is better than that of shallow neural networks.Although the complexity of the model is high,the accuracy of wind-speed prediction and stability are also high.The proposed model effectively improves the accuracy of ultrashort-term wind-speed forecasting in wind farms.
文摘Based on wind-speed records of Alaska’s 19 first-order weather stations, we analyzed the near-surface wind-speed stilling for January 1, 1984 to December 31, 2016. With exception of Big Delta that indicates an increase of 0.0157 m·s–1·a–1, on average, all other first-order weather stations show declining trends in the near-surface wind speeds. In most cases, the average trends are less then?–0.0300?m·s–1·a–1. The strongest average trend of?–0.0500?m·s–1·a–1 occurred at Homer, followed by?–0.0492?m·s–1·a–1 at Bettles, and?–0.0453?m·s–1·a–1 at Yakutat, while the declining trend at Barrow is marginal. The impact of the near-surface wind-speed stilling on the wind-power potential expressed by the wind-power density was predicted and compared with the wind-power classification of the National Renewable Energy Laboratory and the Alaska Energy Authority. This wind-power potential is, however, of subordinate importance because wind turbines only extract a fraction of the kinetic energy from the wind field characterized by the power efficiency. Since wind turbine technology has notably improved during the past 35 years, we hypothetically used seven currently available wind turbines of different rated power and three different shear exponents to assess the wind-power sustainability under changing wind regimes. The shear exponents 1/10, 1/7, and 1/5 served to examine the range of wind power for various conditions of thermal stratification. Based on our analysis for January 1, 1984 to December 31, 2016, Cold Bay, St. Paul Island, Kotzebue, and Bethel would be very good candidates for wind farms. To quantify the impact of a changing wind regime on wind-power sustainability, we predicted wind power for the periods January 1, 1984 to December 31, 1994 and January 1, 2006 to December 31, 2016 as well. Besides Big Delta that suggests an increase in wind power of up to 12% for 1/7, predicted wind power decreased at all sites with the highest decline at Annette (≈38%), Kodiak (≈30%), King Salmon (≈26%), and Kotzebue (≈24%), where the effect of the shear exponents was marginal. Bethel (up to 20%) and Cold Bay (up to 14%) also show remarkable decreases in predicted wind power.
